Rich Models for Steganalysis of Digital Images

Abstract

Abstract-We describe a novel general strategy for building steganography detectors for digital images. The process starts with assembling a rich model of the noise component as a union of many diverse submodels formed by joint distributions of neighboring samples from quantized image noise residuals obtained using linear and non-linear high-pass filters. In contrast to previous approaches, we make the model assembly a part of the training process driven by samples drawn from the corresponding cover-and stego-sources. Ensemble classifiers are used to assemble the model as well as the final steganalyzer due to their low computational complexity and ability to efficiently work with high-dimensional feature spaces and large training sets. We demonstrate the proposed framework on three steganographic algorithms designed to hide messages in images represented in the spatial domain: HUGO, edgeadaptive algorithm by Luo et al. [32], and optimallycoded ternary ±1 embedding. For each algorithm, we apply a simple submodel-selection technique to increase the detection accuracy per model dimensionality and show how the detection saturates with increasing complexity of the rich model. By observing the differences between how different submodels engage in detection, an interesting interplay between the embedding and detection is revealed. Steganalysis built around rich image models combined with ensemble classifiers is a promising direction towards automatizing steganalysis for a wide spectrum of steganographic schemes. I. IntroductionModern feature-based steganalysis starts with adopting an image model (a low-dimensional representation) within which steganalyzers are built using machine learning tools. The model is usually determined not only by the characteristics of the cover source but also by the effects of embedding [4] [33], which was seemingly proposed from a pure cover model, is in reality, too, driven by a specific case of steganography. The choice of the order of the Markov process as well as the threshold T and the

First Steps Toward Camera Model Identification With Convolutional Neural Networks

“…The latter is selected as the algorithm with most promising performances on small image patches. Specifically, within the set of strategies tested in [18], we selected the one denoted as SPAM [29], which outperforms [16], [30] and [31]. Experimental Setup.…”

Steganalysis of LSB Replacement Using Parity-Aware Features

“…For such embedding operations, the most accurate detectors today are built as classifiers using features obtained as sampled joint distributions (co-occurrence matrices) among neighboring elements of noise residuals [12,11,27,25,13]. These detectors perform equally well for both LSB replacement and LSB matching because features formed from noise residuals are generally blind to pixels' parity.…”

Ternary Bose - Chaudhuri - Hocquenghem (BCH) with t = 2 code for steganography

“…Ensemble classifier steganalysis uses a set of 22510 features [16]. A set of 20000 images from BOSS image data [20]has been used for experiments.…”

“…Efficiency of the steganalysis mostly depends on the extracted features. In order to increase accuracy of the stego/cover image classifier modern steganalysis uses extremely large feature sets (10.000 -40.000 features) [16], [17]. The extra large features set has higher chance to define artificial changes done by steganography.…”